Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3271 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2708. Min Range: -5.2708
Max Act: 5.2708. Min Act: -0.1700
Data Index: 6676404 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2708. Min Range: -5.2708
Max Act: 5.2396. Min Act: -0.1700
Data Index: 2192915 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2708. Min Range: -5.2708
Max Act: 5.1458. Min Act: -0.1700
Data Index: 4543855 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2708. Min Range: -5.2708
Max Act: 5.1458. Min Act: -0.1700
Data Index: 1334159 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2708. Min Range: -5.2708
Max Act: 5.1458. Min Act: -0.1700
Data Index: 8699279 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2708. Min Range: -5.2708
Max Act: 5.1458. Min Act: -0.1700
Data Index: 2192916 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2708. Min Range: -5.2708
Max Act: 5.0521. Min Act: -0.1700
Data Index: 6949059 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2708. Min Range: -5.2708
Max Act: 4.9896. Min Act: -0.1700
Data Index: 2366517 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2708. Min Range: -5.2708
Max Act: 4.9583. Min Act: -0.1700
Data Index: 8750381 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2708. Min Range: -5.2708
Max Act: 4.9583. Min Act: -0.1700
Data Index: 3866935 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2708. Min Range: -5.2708
Max Act: 4.9271. Min Act: -0.1700
Data Index: 6482110 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2708. Min Range: -5.2708
Max Act: 4.9583. Min Act: -0.1700
Data Index: 88584 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2708. Min Range: -5.2708
Max Act: 4.8958. Min Act: -0.1700
Data Index: 3722768 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2708. Min Range: -5.2708
Max Act: 4.8958. Min Act: -0.1700
Data Index: 2336108 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2708. Min Range: -5.2708
Max Act: 4.8958. Min Act: -0.1700
Data Index: 5276868 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2708. Min Range: -5.2708
Max Act: 4.8958. Min Act: -0.1700
Data Index: 1346599 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2708. Min Range: -5.2708
Max Act: 4.8646. Min Act: -0.1700
Data Index: 1841077 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2708. Min Range: -5.2708
Max Act: 4.8646. Min Act: -0.1700
Data Index: 3979020 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2708. Min Range: -5.2708
Max Act: 4.8333. Min Act: -0.1700
Data Index: 4618432 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2708. Min Range: -5.2708
Max Act: 4.8333. Min Act: -0.1700
Data Index: 1693261 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19